Mechanistic Shaping uses model's own concepts to write training rules
fatihdin4en · x · 2026-11-06
Thomas Fel et al. propose that a science of post-training can be built on interpretability: models know when they reward hack and we can observe it, yet training ignores this signal. Their Mechanistic Shaping method uses the model's own internal concepts to write training rules, validated across vision, DPO, and RL settings, with analysis of effects on monitoring. Details in the thread.
More from Research
- Making the planet's surface queryable by AI: Luke Davis unveils months-long project — dansitu · 2026-11-06
- Paul Dirac on where good ideas come from: relaxed Sunday walks, not active striving — CatAstro_Piyush · 2026-11-06
- GPT-6 Astra tops a 16-benchmark robot index, yet went 0/11 on real plug insertions — AIFlow_ML · 2026-11-06
- Probability reasons, statistics quantifies, ML predicts — Tivadar Danka untangles the three — TivadarDanka · 2026-11-06
- Burkov's True Positive Weekly #184: LLMs Can Natively Read & Write Neural Network Weights — burkov · 2026-11-06
- Six Claude agents lived 20 days in a simulated town and spontaneously built tools to cooperate — LiminalWanderings · 2026-11-06